PatientAct：基于理论的心理健康来访者模拟
PatientAct: Theory-Grounded Mental Health Client Simulation
查看机构详情
- Tsinghua University（清华大学）
- Beijing Normal University（北京师范大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
PatientAct是基于临床理论的来访者模拟框架，通过整合5Ps临床案例 formulation与带信任阈值的动态记忆层，生成高临床合理性的多样化来访者，在40种临床情境中较基线方法显著提升了抗拒质量与行为真实性。
中文摘要 AI 辅助
基于大语言模型（LLM）的模拟来访者正越来越多地用于培训新手咨询师、评估LLM therapists以及生成合成数据。然而，当前的模拟器生成的来访者过于配合，会轻易披露信息、毫无抗拒地接受治疗重构，并在单次咨询中解决核心问题。我们将这些问题归因于缺乏因果深度的来访者画像，以及将所有内容视为同等可访问的行为机制。我们提出PatientAct，一个基于成熟临床理论的来访者模拟框架。我们的画像整合了5Ps临床案例 formulation，提供因果深度，同时不将设计绑定到任何单一治疗模式。在模拟过程中，画像包含一个动态记忆层，其中的条目带有信任阈值（例如，症状在早期即可获取，而形成性记忆则需要持续的治疗联盟）。在每一轮交互中，来访者的情绪反应和行为会被建模后再生成回应。如果治疗师接近受管控的内容，PatientAct会在数量、内容和风格上表现出抗拒，而非默认选择配合或单一的抗拒模式。我们在40种临床情境中评估了该框架，证明它能生成具有高临床合理性的多样化画像。此外，PatientAct显著优于基线方法，在抗拒质量和行为真实性上取得了实质性提升。我们的代码和数据将通过此http URL公开提供。
英文摘要
LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data. However, current simulators produce overly cooperative clients that disclose too readily, accept therapeutic reframes without resistance, and resolve core issues within a single session. We trace these issues to profiles that lack causal depth and behavioral mechanisms that treat all content as equally accessible. We present PatientAct, a framework for client simulation grounded in established clinical theories. Our profiles integrate the 5Ps clinical case formulation, providing causal depth without tying the design to any single therapeutic modality. During simulation, profiles include a dynamic memory layer in which items carry trust thresholds (e.g., symptoms are available early, whereas formative memories require a sustained therapeutic alliance). At each turn, the client's emotional reaction and behavior are modeled before generating a response. If the therapist approaches gated content, PatientAct expresses resistance in terms of quantity, content, and style rather than defaulting to cooperation or a single resistance pattern. We evaluate our framework on 40 clinical situations and demonstrate that it generates diverse profiles with high clinical plausibility. Moreover, PatientAct significantly outperforms the baselines, yielding substantial gains in resistance quality and behavioral realism. Our code and data are publicly available via github.com/Sahandfer/PatientHub.
